JP2017207872A - Sensor setting location support device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a sensor setting location support device that can appropriately determine a setting location of a sensor such as a camera in consideration of a human flow.SOLUTION: A sensor setting location support device 1 has: a measurement model creation unit 3 that creates a measurement model indicative of a measurement range of a sensor on the basis of characteristic information on the sensor and measurement item information thereon; a human flow map creation unit 4 that creates a human flow map indicative of a human flow direction of a monitoring target region on the basis of map information on the region and human flow information on the region; and a sensor arrangement adjustment unit 5 that calculates measurement sensitivity for each cell constituting the region on the basis of the measurement model and the human flow map, and determines an arrangement location of the sensor in the region on the basis of the calculated measurement sensitivity. The measurement model includes measurement accuracy in accordance with a distance from the sensor and a measurable range therein, in which, when a ratio to 1 is A, the measurement sensitivity is a value that multiplies a ratio of an area of A of measurement accuracy to an area of the cell by A.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a technique for determining the arrangement of a plurality of sensors that perform object detection and position measurement.

  In public facilities such as large commercial facilities, stations, and airports, in addition to conventional crime prevention services such as detection of people and suspicious objects, measuring and tracking the position of people can increase the spatial value of marketing, congestion reduction, layout improvement, etc. The demand for enhanced services is increasing. Although these services can be realized by installing a plurality of sensors such as a monitoring camera and a laser radar and referring to each measurement result, the arrangement of the sensors is important in order to maintain stable measurement accuracy.

  For example, if it is desired to detect a suspicious person, it is necessary to install a sensor so as not to cause a blind spot, and if it is desired to track a person, it is necessary to determine the position of the sensor so that the movement trajectory of the person can be measured without interruption. . For this reason, when introducing a service, the experts who actually perform the installation work decide the sensor placement and setting based on their own know-how based on the needs of customers.

  However, this method not only leads to an increase in the installation cost, but also the measurement accuracy depends on the difference in knowledge and experience of specialists. Therefore, a support technology for automatically determining the sensor installation position is required.

  For example, in Patent Document 1, in a commercial facility, an area where people are likely to gather is estimated according to information such as POS (Point of Sales) data and customer sex, thereby determining camera distribution and installation position. Moreover, in patent document 2, the optimal installation position of a surveillance camera is automatically output according to a customer's measurement needs, such as detecting a suspicious person or a motion.

JP 2005-286619 A JP 2012-10210 A

  In Patent Document 1, although the installation position of the camera can be estimated, there is a problem that detailed installation information such as the installation angle of the camera such as the depression angle cannot be output. Further, it is necessary to determine the total number of cameras to be used in advance, and expert know-how is required for the determination.

  In Patent Document 2, the camera installation position can be automatically estimated from the layout of the shooting range and the customer needs table with a configuration that requires a minimum number of cameras. However, there is room for further improvement in cases where it is desired to perform high-precision measurement depending on the situation and to use sensors other than the surveillance camera in consideration of the movement of people such as actual human flow in the shooting range.

  The present invention is an invention for solving the above-described problem, and an object thereof is to provide a sensor installation position support device capable of appropriately determining the installation position of a sensor such as a camera in consideration of human flow. To do.

  In order to achieve the above object, the sensor installation position support device of the present invention is a measurement model generation unit (for example, a measurement model generation unit) that generates a measurement model indicating a measurement range of the sensor based on sensor characteristic information and measurement item information. Part 3), a human flow map generating means (for example, a human flow map) for generating a human flow map (for example, 23 in FIG. 4) indicating the flow direction of the area based on the map information of the monitored area and the human flow information of the area. A sensor arrangement that calculates the measurement sensitivity (for example, Equation 1) for each cell constituting the area based on the generation unit 4), the measurement model, and the human flow map, and determines the position of the sensor in the area based on the calculated measurement sensitivity It has a determination means (for example, sensor arrangement adjustment part 5), It is characterized by the above-mentioned. Other aspects of the present invention will be described in the embodiments described later.

  According to the present invention, it is possible to appropriately determine the installation position of a sensor such as a camera in consideration of human flow.

It is a figure which shows the functional block of the sensor installation position assistance apparatus which concerns on Embodiment 1. FIG. It is a figure which shows an example of the characteristic information of the sensor which a measurement model production | generation part acquires. It is a figure which shows an example of the measurement model produced | generated by the measurement model production | generation part. It is a figure explaining the process of a human flow map production | generation part. It is a flowchart which shows the process of a human flow map production | generation part. It is a figure which shows the functional block of a sensor arrangement | positioning adjustment part. It is a figure which shows an example of the important measurement point output by a measurement center point detection part. It is a flowchart which shows the process of a measurement model collation part. It is a figure explaining process S3 of a measurement model collation part, (a) is a person flow map, (b) is a measurement direction of a measurement model, (c) is a figure which shows the installation position of a camera. It is a figure explaining process S5 of a measurement model collation part, (a) is a measurement model, (b) is a measurement model collated with human flow map 51, (c) (d) is an enlarged view of a cell in a human flow map. is there. It is a figure explaining process S4 of a measurement model collation part. It is a figure which shows an example which collates a measurement model by a measurement model collation part. It is a figure which shows an example of the sensor position output by a sensor arrangement | positioning adjustment part. It is a figure which shows the functional block diagram of the sensor installation position assistance apparatus which concerns on Embodiment 2. FIG. 10 is a flowchart illustrating processing of a sensor arrangement adjustment unit according to the second embodiment. It is a figure which shows an example of the sensor position adjusted by a sensor arrangement | positioning adjustment part.

DESCRIPTION OF EMBODIMENTS Embodiments for carrying out the present invention will be described in detail with reference to the drawings as appropriate.
<< Embodiment 1 >>
FIG. 1 is a functional block diagram of the sensor installation position support apparatus 1 according to the first embodiment. In this embodiment, an example in which a surveillance camera is used as a sensor will be described. However, the present invention is not limited to these sensors, and different types of sensors may be used in combination.

  The sensor installation position support device 1 holds a database 2 including map information 100, human flow information 101, sensor information 102, and measurement item information 103 of a target area, and a measurement model generation unit 3 (measurement model generation) as a processing unit. Means), a human flow map generation unit 4 (human flow map generation unit), and a sensor arrangement adjustment unit 5 (sensor arrangement determination unit). The sensor installation position support device 1 is a device that automatically outputs a sensor arrangement that provides the best measurement sensitivity of the target area based on each information.

  First, the outline of each function shown in FIG. 1 will be described. The measurement model generation unit 3 is a function for determining a measurement model indicating the measurement range of the sensor from the sensor information 102 and the measurement item information 103, and the human flow map generation unit 4 is a target area. A function for creating a human flow map showing the flow of people in the target area based on the map information 100 and the human flow information 101, the sensor arrangement adjusting unit 5 matches the measurement model with the human flow map and determines the sensor position where the measurement sensitivity of the target area is the best. Has a function to output. The target area is a range that the customer wants to measure with a sensor. For example, in the case of a camera, the monitoring target area is indicated, and in the case of a laser radar, the measurement target area is indicated. Details of each function will be described below.

<Measurement model generator>
FIG. 2 is a diagram illustrating an example of sensor characteristic information acquired by the measurement model generation unit 3. FIG. 3 is a diagram illustrating an example of a measurement model generated by the measurement model generation unit 3. The measurement model generation unit 3 will be described with reference to FIG. 1 as appropriate using FIG. 2 and FIG.

  FIG. 2 is an example of sensor characteristic information acquired by the measurement model generation unit 3 from the sensor information 102. In each sensor, the measurable range, the measurement accuracy according to the distance from the sensor to the measurement person, and the density of people. The measurement accuracy (resolution) according to the degree and the features of the items (measurement items) that can be measured by the sensor are shown. The sensor and the characteristic information are not particularly limited to this, and the characteristic information whose range, accuracy, and resolution are changed according to the measurement item even in the same sensor may be used. In addition, the measurement accuracy does not necessarily have to be different depending on the distance, and the characteristic information may be that the accuracy of the entire measurement range is uniform.

  The measurement model generation unit 3 generates a sensor measurement model as shown in FIG. 3 by collating customer measurement needs such as person tracking and suspicious person detection extracted from the measurement item information 103 with sensor characteristic information. In FIG. 3, 10 is a monocular camera, 11a and 11b are examples of a measurement model for human tracking and object detection of the monocular camera, 12 is a laser sensor, and 13a and 13b are measurement models for human tracking and object detection of the laser sensor. An example is shown.

  The shape of the measurement model is not changed depending on the measurement item as shown in FIG. As a factor to use the method of changing the shape of the model depending on the measurement item, for example, compared to object detection that detects objects existing in the target area, it is measured by human tracking that recognizes an object as a person and follows it Since the measurement range and accuracy are different, the size of the shapes of 11a and 13a is smaller than 11b and 13b even in the same sensor. In general, a camera uses a measurement model whose accuracy changes according to the distance from the sensor 10, such as 11a and 11b, in order to express characteristics such as difficulty in detecting an object that is too close or far away. May be. The shape of the measurement model is not particularly limited to that shown in FIG. In addition, the information used for generating the measurement model is not limited to the sensor characteristics and the measurement item information, but map information in the building may be used, for example, the height of the installation location or the depression angle. A method of making the shape of the measurement model variable is also possible.

  That is, the measurement model generation unit 3 (measurement model generation means) uses at least one or more of layout information, person flow direction information, position environment information, and congestion status information of the target area, and / or measurement range of the measurement model. The accuracy may be changed. Here, the layout information of the target area includes map information, the height of the building, the entrance of the building, and the like. The human flow direction information includes a human flow map generated by the human flow map generating means. The position environment information includes the environment of the measurement position such as backlight and indoor / outdoor. The congestion status information is information on whether or not the place is easy for people to gather, such as whether it is busy or busy.

<Human flow map generator>
FIG. 4 is a diagram for explaining processing of the human flow map generation unit 4 (see FIG. 1). FIG. 5 is a flowchart showing the processing of the human flow map generation unit 4. The human flow map generation unit 4 will be described with reference to FIGS. 4 and 5.

  First, the human flow map generation unit 4 obtains a layout overhead view 20 (layout information) of the target area shown in FIG. 4 from the map information 100 (processing S41), and a plurality of layout overhead views as shown in FIG. Divide into small areas (process S42). Next, the human flow data 22 in the target area is extracted from the human flow information 101 (processing S43), and the direction of the main human flow in each small area is estimated (processing S44). Finally, the human flow map 23 reflecting the direction of the human flow in the layout overhead view is output (processing S45). In the following description, this small area is referred to as a cell.

  As a method of dividing the cell in the layout overhead view 10 in the process S42, the size of the cell only needs to be smaller than that of the measurement model, and it is not necessary that all the cells have the same size. Further, the shape is not particularly limited as long as it can cover the whole overhead view other than the lattice shape like 21.

  The human flow data acquired in step S43 may be information that can estimate the main direction of the human flow in the target area, such as human trajectory information. For example, if there is already a person who actually moves in the target area, data obtained by temporarily placing a sensor for measuring human flow, and if there is no person, the doorway or corner in the layout overhead view Human flow data estimated by simulation from the above information may be used, and is not particularly limited.

  In process S44, the direction 24 of the human flow in each grid of the layout overhead view is determined from the acquired human flow data 22. As a method of estimating the direction 24 of the human flow, there is a method of collating the human flow data 22 with 21 and estimating a direction vector having the highest frequency with the center of the grid as the origin. In the present embodiment, the direction of the human flow is set to four patterns as in 24, and the final direction of the human flow is determined by comparing which direction pattern the direction vector estimated in each lattice is similar to. . Note that the number of patterns in the direction of human flow is not limited to four, and the accuracy of sensor arrangement can be improved as the number of patterns increases.

<Sensor placement adjustment unit>
FIG. 6 is a diagram illustrating functional blocks of the sensor arrangement adjustment unit 5. The sensor arrangement adjustment unit 5 will be described with reference to FIG. The sensor arrangement adjustment unit 5 has functions of a measurement center point detection unit 30, a measurement model collation unit 31, and a sensor arrangement position output unit 32. The outline of each function will be explained. The measurement center point detection unit 30 is a function for determining an important measurement point indicating the center position of the measurement in the target area from the information of the human flow map, and the measurement model collating unit 31 The function of updating the measurement sensitivity of all cells in the target area by collating with the human flow map centering on the measurement point, the sensor arrangement position output unit 32 outputs the sensor position information from the optimized sensitivity map information It has the function to do. Details of each function will be described below.

  FIG. 7 is a diagram illustrating an example of important measurement points (candidate measurement points) output by the measurement center point detection unit 30. As a method for determining important measurement points, a search window 40 including four cells is scanned, and two conditions are set such that “all cells contain human flow direction information” and “maximum distribution of human flow directions”. There is a method of searching for four adjacent cells to satisfy and using the center position as an important measurement point (candidate measurement point).

  The reason for the former is to implement efficient sensor placement by excluding areas such as walls, which are one of the layout information, from non-existent areas, and the latter reason is to understand human flow information. This is because a point (congestion state information) with a large change in the direction of human flow (human flow direction information) has a high probability of being an important measurement target when tracking a person or a person.

  In addition, as a method of determining important measurement points, a method of determining the position of the entrance of a building, which is position environment information, from map information, or a method of manual setting by a user using a GUI (Graphical User Interface) or the like There is no particular limitation as long as the number of important measurement points can be determined one or more. Further, the measurement method of the important measurement points may be switched depending on the measurement item. For example, when the measurement item is person tracking, the method shown in FIG. 7 may be used, and when the suspicious person is detected, the method of determining the position of the entrance / exit of the building considered as the central area of measurement from the map information may be used.

  That is, the measurement center point detection unit (important measurement point detection unit) performs measurement in the target area using at least one of layout information, person flow direction information, position environment information, and congestion status information of the monitoring target area. One or more important points should be extracted.

  FIG. 8 is a flowchart showing the processing of the measurement model matching unit 31. In the measurement model collation unit 31, first, a measurement model is acquired from the measurement model generation unit 3 (processing S1). Subsequently, the measurement sensitivity of the cell near the important measurement point detected by 30 is confirmed (processing S2), and if it is less than the threshold value (processing S2, No), the measurement model is collated with the important measurement point (S3), and the threshold value is exceeded. If so (Processing S2, Yes), after creating a new important measurement point centering on the vicinity of the cell where the measurement sensitivity is not set (Processing S4), the process S3 is performed. And the value of the measurement sensitivity of each cell with which the measurement model was collated is updated (process S5), and it is confirmed whether the measurement sensitivity of all the cells in the target area is equal to or higher than the threshold (process S6). If it is less than the threshold value (No at Step S6), the process returns to Step S2, and if it is equal to or greater than the threshold value (Step S6, Yes), the process of the measurement model matching unit 31 is terminated. The sensor arrangement position output 32 (see FIG. 6) outputs the sensor arrangement position. Hereinafter, a method for collating the measurement model in the process S3, a method for creating an important measurement point in the process S4, and a method for calculating the measurement sensitivity in the step S5 will be described in detail.

  FIG. 9 is a diagram for explaining the processing S3 of the measurement model collation unit 31, where (a) is a human flow map, (b) is a measurement direction of the measurement model, and (c) is a diagram illustrating a camera installation position. The process S3 will be described with reference to FIG. Here, when the measurement item is person tracking, a flow for collating the camera measurement model with the human flow map 51 in which the important measurement points 50 shown in FIG. 9A are set will be described.

  9B is an enlarged view of the vicinity of the important measurement point 50, 53 is a camera, 54 is a measurement model of 53, 55 is a center line of the measurement model, 56a, 56b, and 56c are human flows centered on 50. A straight line representing the orientation of the sensor, 57 is an overlapping portion of the area outside the target area and the measurement model area, and 58 is a straight line connecting the sensor installation position and the important measurement point.

  In the process S3, after first determining the installation position of the measurement model 54 in the human flow map, an optimal measurement direction is estimated from the direction of the human flow. As a method of determining the installation position 54, there is a method of matching the center of gravity of the measurement model with the important measurement point 50. Other methods include setting the center of gravity of the region with the highest measurement accuracy in the measurement model, or providing the measurement model with position information with the highest measurement accuracy acquired from sensor information in advance when generating the measurement model. However, there is a method of matching the position with the important measurement point, and there is no particular limitation.

  Next, a method for estimating the measurement direction of the measurement model will be described. When tracking a person using a camera, tracking tends to be easier for a person who moves in a vertical direction than a horizontal movement with respect to the camera. In addition, the suspicious person detection also has an advantage that the face of the suspicious person can be easily photographed by photographing from the vertical direction.

  Therefore, in this example, the direction in which the angles θa, θb, and θc formed by the center line 55 of the measurement model and the straight lines 56a, 56b, and 56c representing the direction of each person flow are equal to or less than a certain value is set as a measurement model direction candidate. The direction in which the overlapping area 57 of the measurement target area such as a wall and the measurement model is the minimum is the direction of the final measurement model.

  If the installation position of the camera 53 is set in an area that is not an installation target such as a wall or outside the human flow map from the collated measurement model, the installation position and the important measurement point are represented by a straight line 58 (FIG. 9C). Finally, the measurement model may be translated so that the installation position is included in the installation target. Further, when the optimum measurement model position is output as a plurality of candidates by the above-described method, it is possible to cope with the method of automatically selecting one or the method of manually selecting one. In addition, you may refer to map information etc. to determine the measurement direction of the measurement model.For example, priority is given to the direction in which the entrance / exit can be photographed in order to place importance on the photographing of people coming in and out, and measurement by disturbance such as backlighting. In order to prevent a decrease in accuracy or protect privacy, a method of giving priority to a direction in which the outdoor is not photographed may be adopted.

  FIG. 10 is a diagram for explaining the processing S5 of the measurement model collation unit 31. (a) is the measurement model 60, (b) is the measurement models 60a and 60b collated with the human flow map 51, and (c) and (d) are It is an enlarged view of the cell in the human flow map. Before describing the process S4, the process S5 for calculating the measurement sensitivity of the cell will be described with reference to FIG.

  In FIG. 10A, 60 is a measurement model, in FIG. 10B, 60a and 60b are measurement models collated with the human flow map 51 by the process S3, and 61a and 61b are enlarged views of two cells in the human flow map. ing. In FIG. 10C, only the measurable region of the measurement model 60b exists in the cell 61a, 62 indicates a region with a measurement accuracy of 90%, and 63 indicates a region with a measurement accuracy of 70%. In FIG. 10D, in the cell 61b, there are both measurable regions of the measurement models 60a and 60b, 64 is a region with a measurement accuracy of 40% of 60a, and 65 is a measurement accuracy of 40b with 60%. An area 66 indicates an overlapping area of 60a and 60b with a measurement accuracy of 40%. The measurement sensitivity when there is no overlap with other regions such as regions 62, 63, 64, and 65 can be derived from [Equation 1].

  When there is an overlap as in the region 66, it can be derived by obtaining the average of the measurement sensitivities obtained in [Equation 1]. The total measurement sensitivity of each region is the measurement sensitivity of the cell including that region. The method for calculating the measurement sensitivity is not particularly limited as long as it can be calculated for each cell, and the value can be relatively compared between cells in consideration of the measurement accuracy of the sensor.

  FIG. 11 is a diagram for explaining the process S <b> 4 of the measurement model collation unit 31. The process S4 will be described with reference to FIG. In FIG. 11, 70 is an example of a human flow map in which measurement sensitivity is reflected, 71 is an important measurement point, 72 is a measurement sensitivity value of each cell, and 73 is a measurement sensitivity existing in the vicinity of the important measurement point is a threshold (30 in this example). ) Cells 74 a, 74 b, 74 c, 74 d, and 74 e indicate position candidates of important measurement points to be newly created. In the process S4, the positions of important measurement points are determined so that many 73 measurement sensitivities are equal to or higher than a threshold value under preset conditions.

  As the method for determining the position, as shown in the example of FIG. 11, the grid points where the measurement sensitivity has been calculated and the cell 73 are in contact are candidates, and “all four surrounding cells are within the target area”, “important measurement points” There is a method of outputting the final position based on a condition such as “the distance is close to”. In this example, 74c is a position candidate.

  Note that the position candidates are not limited to grid points, but may be cell center points or grid lines, or may use map information such as “prioritize cells close to the entrance / exit”, particularly limited to the above conditions. Not.

  In the present embodiment, by repeatedly performing the processing S4 and the processing S3, the measurement sensitivity of each cell is updated, and the sensor position where the measurement accuracy of the entire target area is optimized is output. Therefore, when the process S3 is performed, the measurable area of the measurement model already matched with the important measurement point and the measurement model of the measurement model according to the new important measurement point may overlap. The position and orientation of the measurement model may be adjusted.

  FIG. 12 is a diagram illustrating an example of collating a measurement model by the measurement model collating unit 31. For example, as shown in FIG. 12, when the measurement model 80b is collated with the important measurement point 81 obtained in step S4, an overlapping area 82 with the measurement model 80a is generated. In this case, since detection of a suspicious person, etc. requires that a sensor be installed so that no blind spot is generated in the target area, it is preferable to increase the priority of the measurement method in which the overlapping area 82 is reduced. In the case of person tracking, since the measurement accuracy increases as the number of overlapping regions 82 increases, it is preferable to increase the priority of the measurement direction in which the overlapping region 82 has an area of a certain ratio or more of the measurement model. Moreover, the method of adding the ratio of the overlapping area 82 in each cell to the conditions which determine a measuring method may be sufficient, and it does not specifically limit.

  The sensor arrangement position output unit 32 (see FIG. 6) outputs the final sensor arrangement position from the position information of the measurement model in the human flow map acquired by the measurement model matching unit 31.

  FIG. 13 is a diagram illustrating an example of the sensor position output by the sensor arrangement adjustment unit 5. By the processing described above, the sensor arrangement adjustment unit 5 determines the positions of all the sensors for each important measurement point in the target area as shown in FIG.

  The sensor arrangement adjusting unit 5 (sensor arrangement determining means) of the present embodiment determines the sensor arrangement position based on the measurement model and the human flow map, but is not limited thereto. The sensor arrangement adjustment unit 5 may determine the arrangement position of the sensor using at least one or more of layout information of the target area, human flow direction information, position environment information, and congestion status information.

  Note that the measurement model used in the sensor arrangement adjustment unit 5 may be the same sensor but different shapes. For example, since the height at which the sensor is arranged can be acquired from the position of the measurement model collated with the map information and the important measurement point, the measurement model generated from the height information may be collated with the human flow map by processing S3.

  In addition, it is possible to determine a target area that is likely to be congested or quiet based on human flow information, and collate a measurement model whose measurement accuracy has changed within that area to calculate the measurement sensitivity of each cell. You can determine the measurement direction.

  Note that different sensor measurement models may be used in the sensor arrangement adjustment unit 5. For example, basically the camera measurement model is collated with the human flow map, and if the cell human flow direction is the same in a wide area, it is determined that the area is unlikely to be crowded, and the laser radar measurement model is The method of collating may be used. In this case, for example, it may be added as an optimization condition by having the user specify the number of cameras and laser radars to be used in advance or the total cost.

  Further, when using a measurement model of a different sensor in the sensor arrangement adjustment unit 5, for example, in the case of the process S3 in FIG. 8, when the overlapping ratio of the measurement range of the verified measurement model and the new model is large There is a method of minimizing the number of installed sensors by adding a process of changing the measurement model and selecting the one with a lower duplication rate.

  The sensor arrangement adjustment unit 5 outputs not only one sensor arrangement pattern but also a plurality of patterns. For example, when determining the sensor position at an important measurement point, if the same measurement sensitivity is shown in two measurement directions, either one is selected and the sensor arrangement is output, then the other is selected. A method in which the sensor arrangement is output and the user finally selects, or a method in which the higher one is automatically selected by comparing the calculated measurement sensitivities of the entire target area may be used.

  In Embodiment 1 of the present invention, with the functional configuration described above, a measurement model corresponding to sensor characteristics and measurement items is generated, and the measurement sensitivity is calculated by collating with a human flow map created from the layout information of the measurement range. The arrangement positions of a plurality of sensors can be automatically output.

  In the first embodiment, the camera installation position can be output using not only the two-dimensional space but also the information of the three-dimensional space. For example, instead of a human flow map obtained by dividing a two-dimensional map into cells, a human flow map obtained by dividing a three-dimensional space into a plurality of voxels is used, and the direction and measurement sensitivity of the human flow of each voxel are derived using a three-dimensional measurement model. Thus, the series of flows in FIG. 1 may be performed.

<< Embodiment 2 >>
FIG. 14 is a functional block diagram of the sensor installation position support apparatus 1A according to the second embodiment. Compared to FIG. 1, the sensor installation position support apparatus 1 </ b> A includes a sensor information acquisition unit 6 and a human flow information acquisition unit 7, and the sensor installation information 104 acquired by the sensor information acquisition unit 6 is stored in the database 2. ing. In the second embodiment, in a situation where a sensor has already been installed, the sensor installation method is corrected and a new sensor arrangement position is output.

  The sensor placement adjustment unit 5A calculates the overall measurement sensitivity from the information of the sensors already installed in the target area, determines the area where the measurement sensitivity is low, and corrects the sensor installation method to improve the sensitivity. In some cases, a new sensor installation position is output. The details of the sensor arrangement adjustment unit 5A will be described below.

  FIG. 15 is a flowchart illustrating processing of the sensor arrangement adjustment unit according to the second embodiment. In FIG. 15, processes S2, S4, S5 and S6 are the same as the processes in FIG. First, the sensor arrangement adjustment unit 5A calculates the measurement sensitivity of all cells in the target area from the human flow map of the target area and the measurement model of the currently installed sensor (processing S20). Next, one or more initial positions of important measurement points in the target area are determined by using a method similar to that of the measurement center point detection unit 30 in FIG. 6 (processing S21).

  Then, the sensor arrangement adjustment unit 5A determines whether or not the measurement sensitivity of the cell near the important measurement point is equal to or higher than the threshold (processing S2). If the measurement sensitivity of the cell in the vicinity of the important measurement point is equal to or higher than the threshold value (step S2, Yes), a new important measurement point is created (step S4), and the process proceeds to step S22. If the measurement sensitivity of the cell near the important measurement point is less than the threshold (No at Step S2), the process proceeds to Step S22.

  In process S22, it is determined whether an existing measurement model (a measurement model of a currently installed sensor) exists in the vicinity of an important measurement point. Specifically, the distance between the important measurement point and the position of the existing measurement model is calculated. In addition, as a confirmation method of process S22, if it is a method which can compare especially a positional relationship, it will not specifically limit.

  If it is determined in step S22 that no existing measurement model exists (No in step S22), a new measurement model is acquired from the measurement model generation unit 3, and an important measurement model is obtained by the same process as the process S3 in FIG. (Step S23), and the process proceeds to step S5.

  On the other hand, when it is confirmed by the process S22 that the existing measurement model exists (process S22, Yes), the existing measurement model is collated with the important measurement point (process S24), and the process proceeds to the process S5. In addition, as process S24, since the position of the measurement model is fixed, only the measurement direction is adjusted, and the method may be the same process as process S3.

  Finally, the measurement sensitivity of the cell with which the measurement model is collated is updated (processing S5). If the measurement sensitivity of all the cells in the target area is equal to or greater than the threshold value in processing S6 (processing S6, Yes), the processing is performed. If it is less than the threshold (No at Step S6), the process returns to Step S2.

  In the second embodiment, the position of the measurement model in the human flow map when the process is finished by the sensor arrangement adjustment unit 5A is output as the final sensor arrangement position. Note that the sensor placement adjustment unit 5A does not perform a process of creating a new measurement model and collating it according to the user's wish, and collating only the measurement model of the existing sensor with the human flow map to change the measurement direction of the sensor. A correction method may be used.

  FIG. 16 is a diagram illustrating an example of a sensor position adjusted by the sensor arrangement adjustment unit 5A, where (a) shows measurement sensitivity before adjustment, and (b) shows measurement sensitivity after adjustment. FIG. 16 shows an example in which the sensor installation angle is adjusted by the sensor arrangement adjustment unit 5A. In FIG. 16, 53 is a sensor, 60c is a measurement model of 53, 70a and 70b are human flow maps reflecting measurement sensitivity before and after sensor position adjustment by the sensor placement adjustment unit 5A, and 110 is one cell in the target area. Show. For example, when the user sets the measurement sensitivity threshold value to 50, the measurement sensitivity is insufficient in the cell 110. Therefore, by changing the installation angle of 53, the measurement sensitivity of 110 is set to 50. It is possible to output a sensor arrangement in which the measurement sensitivity of the cell is equal to or higher than a threshold value.

  In the second embodiment of the present invention, with the functional configuration described above, the measurement model is collated with the human flow map in consideration of the position information of the sensor already installed in the target area, and the measurement sensitivity is calculated. The installation method can be modified, and a new sensor installation position can be output if necessary.

  In the second embodiment, when creating a human flow map, creating a measurement model, or collating a measurement model with an important measurement point, detecting human flow information or a person measured by an existing sensor acquired by the human flow information acquisition unit 7 Results such as rate may be used. For example, when the human flow changes greatly compared to before the change due to the layout change in the facility, the sensor arrangement suitable for the layout after the change can be output by applying the second embodiment.

  The sensor installation position support apparatus 1 according to the present embodiment includes a measurement model generation unit 3 that generates a measurement model indicating a measurement range of the sensor based on sensor characteristic information and measurement item information, and map information of an area to be monitored. Based on the human flow information of the area, the human flow map generation unit 4 that generates a human flow map indicating the flow direction of the area, and the measurement sensitivity for each cell constituting the area is calculated based on the measurement model and the human flow map. And a sensor arrangement adjustment unit 5 that determines the arrangement position of the sensor in the area based on the measurement sensitivity. Note that the measurement model includes measurement accuracy according to the distance from the sensor and a measurable range, and the measurement sensitivity is such that when the ratio of measurement accuracy to 1 is A, the measurement accuracy for the cell area is A. It is a value obtained by integrating the ratio of the surface line and A.

  By applying the sensor installation position support apparatuses 1 and 1A of the embodiment described above, the installation positions of one or a plurality of sensors can be automatically determined according to the measurement needs of the customer.

1,1A Center installation position support device 2 Database (storage means)
3 Measurement model generator (measurement model generator)
4 Human flow map generation unit (human flow map generation means)
5,5A Sensor arrangement adjustment unit (sensor installation position determining means)
6 Sensor information acquisition unit 7 Human flow information acquisition unit 10 Monocular camera (sensor)
12 Laser sensor (sensor)
11a, 11b, 13a, 13b Measurement model 20 Layout overhead view (layout information)
23 Human flow map 100 Map information 101 Human flow information 102 Sensor information 103 Measurement item information 104 Sensor installation information

Claims (13)

Measurement model generation means for generating a measurement model indicating the measurement range of the sensor based on the sensor characteristic information and the measurement item information;
A human flow map generating means for generating a human flow map indicating the flow direction of the area based on the map information of the area to be monitored and the human flow information of the area;
Sensor placement determining means for calculating measurement sensitivity for each cell constituting the area based on the measurement model and the human flow map, and determining the placement position of the sensor in the area based on the calculated measurement sensitivity. A featured sensor installation position support device. The human flow map generating means acquires the layout information of the area from the map information of the area, divides the acquired layout information into cells constituting the area, and determines the human flow direction for each cell from the human flow information. The sensor installation position support apparatus according to claim 1, wherein the sensor installation position support apparatus is determined. 2. The sensor installation position support device according to claim 1, wherein the sensor arrangement determining unit calculates the measurement sensitivity for each cell by comparing the measurement accuracy included in the measurement model with the human flow map. The sensor arrangement determining means extracts one or more candidate measurement points to be measured in the area by using at least one of the area layout information, human flow direction information, position environment information, and congestion status information, The sensor installation position support apparatus according to claim 1, wherein the measurement model is arranged at the extracted candidate measurement point. The sensor placement determination means determines the placement position of the sensor using at least one or more of layout information, flow direction information, position environment information, and congestion status information of the area. The described sensor installation position support device. The measurement model generation means changes the measurement range or / and measurement accuracy of the measurement model by using at least one of layout information, flow direction information, position environment information, and congestion status information of the area. The sensor installation position support apparatus according to claim 1. The said sensor arrangement | positioning determination means makes the said candidate measurement point vicinity the new said candidate measurement point, when the measurement sensitivity of the said cell near the said candidate measurement point is more than a predetermined threshold value. The sensor installation position support apparatus according to 1. The sensor placement position support device according to claim 4, wherein the sensor arrangement determination unit changes the measurement model so that the measurement sensitivity of the cells in the area is equal to or higher than a predetermined threshold value. The sensor placement position support apparatus according to claim 1, wherein when there are a plurality of placement positions of the sensors, the sensor placement determination unit uses measurement models of different types of sensors. The sensor installation position support device further includes a sensor information acquisition unit that acquires already installed sensor installation information,
The sensor installation position support device according to claim 4, wherein the sensor arrangement determination unit sets the sensor installation position acquired by the sensor information acquisition unit as the candidate measurement point. The sensor according to claim 10, wherein the measurement model generation unit generates a measurement model indicating a measurement range of the sensor based on sensor characteristic information and measurement item information acquired by the sensor information acquisition unit. Installation position support device. The sensor installation position support device further includes a human flow information acquisition unit for acquiring human flow information from an installed sensor,
The sensor installation position support device according to claim 1, wherein the flow information is the human flow information of the area based on the human flow information acquired by the human flow information acquisition unit. The measurement model includes a measurement accuracy according to a distance from the sensor and a measurable range,
The measurement sensitivity is a value obtained by integrating the ratio of the area of A to the area of the cell and the A when the ratio of the measurement accuracy to 1 is A. 5. The sensor installation position support apparatus according to 1.

Images